A persistent configuration tool for Openclaw Skills that allows users to set and manage their primary AI model via commands or interactive pickers.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install default-model
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install default-model using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Default Model Plugin?
The Default Model plugin is a utility designed to streamline how users manage their primary AI model configuration. Unlike session-specific overrides, this skill ensures that your preferred model is written directly to the configuration file, allowing it to persist through gateway restarts and apply automatically to all new sessions. It bridges the gap between manual config editing and user-friendly interaction, making it a staple for anyone utilizing Openclaw Skills.
By integrating directly with the configuration layer, it provides a seamless experience for developers and power users who frequently switch between different LLM providers like OpenRouter or local instances. This tool is essential for maintaining a consistent workflow within the broader ecosystem of Openclaw Skills.
Default Model Plugin Use Cases
- Setting a preferred primary LLM across all new agent sessions without manual config editing.
- Switching between different providers using a visual Telegram picker for Openclaw Skills.
- Ensuring that specific model settings survive system restarts or gateway reboots.
How Default Model Plugin Works
- The user executes the
/default_modelcommand within an environment supporting Openclaw Skills, either with a specific model string or as a standalone command. - If using the Telegram interface, the skill presents a hierarchical picker for selecting the provider and then the specific model.
- Upon selection, the skill updates the
agents.defaults.model.primaryfield within the core configuration file. - The changes are saved persistently, and any new session initiated will automatically adopt the newly defined default model.
Default Model Plugin Setup
To install the plugin and start managing your models, run the following command in your terminal:
openclaw plugins install clawhub:default-model
Default Model Plugin Data Schema & Taxonomy
The skill interacts with the standard configuration file to maintain persistence. Below is the primary data mapping:
| Path | Description |
|---|---|
agents.defaults.model.primary |
The primary key updated by the skill to set the global default model. |
| Config File | The destination where persistent changes are written to survive restarts. |
Default Model Plugin Advanced Features
- Telegram Interactive Picker: A user-friendly UI for provider and model selection within Openclaw Skills.
- Persistent Configuration: Direct writes to the config file ensure settings are not lost on restart.
- Command-Line Flexibility: Supports both manual model string entry and interactive selection.
- Session Isolation: Allows for global defaults without interrupting current active session overrides.
SKILL.md
Loading
Related Openclaw Skills
Sanjiaozhou Action Randomizer
A specialized generator for Delta Force players to randomize maps, weapons, modification codes, and tactical equipment for unique gameplay challenges.
Skill Design Guide
A professional engineering framework for building modular AI capabilities that prioritize workflow migration over simple prompt engineering.
Aliyun Unified Search
A robust web search skill that leverages the Alibaba Cloud Unified Search API to provide AI agents with real-time search results, snippets, and metadata.
SQLBot Workspace & Dashboard Manager
A powerful tool for managing SQLBot workspaces, querying datasources, and exporting analytical dashboards through AI agent commands.
Metacognition
A self-reflection engine for AI agents that extracts patterns into a weighted graph using Hebbian learning and time-based decay.
Deep Thinking Protocol
A comprehensive deep reasoning framework designed to guide systematic, exploratory thinking for complex architectural decisions and high-stakes debugging.
Featured*
